memory-extraction SKILL.md skillA
memory-extraction from lazyisefficient/agentic-os is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add lazyisefficient/agentic-os/memory-extraction@git:20260716.7c29779Pins git:20260716.7c29779 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- lazyisefficient/agentic-os
- Path
.claude/skills/memory-extraction/SKILL.md- Versions recorded
- 4
- Latest version
- git:20260716.7c29779, committed Jul 16, 2026
- First version recorded
- Jul 13, 2026
- Size
- 12,197 bytes
- Repository stars
- 17
- License
- MIT
End-of-session pass that persists durable facts from the CURRENT session into .claude/memory/. Runs IN-SESSION in the main agent (never via Task — a subagent starts cold with no transcript), prompted by the Stop hook's nudge. Triggers on "persist durable facts from this session", "run memory-extraction", "flush session memory", or "extract memory before close". Reads the in-context transcript plus existing memory, applies the durable-fact predicate below, and writes one file per fact plus one…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Memory extraction This skill is the reliable-encoding pass: at the end of a session it reads what just happened and writes the durable facts to `.claude/memory/` so the NEXT cold session starts hot instead of relearning them. It replaces best-effort in-conversation self-classification with a deterministically-triggered flush. It is **self-contained**: the durable-fact predicate and the memory-file mechanics are inlined below. It does NOT depend on `.claude/rules/` or `CLAUDE.md` — those are not installed on consumer machines, so nothing in this skill may assume they exist. ## Invocation contract - **Run in-session, in the main agent.** The only input is the current session transcript, which already sits in the invoking agent's context. There is no argument passing. - **NEVER dispatch this as a `Task`/subagent.** A subagent starts cold with none of the parent's transcript — it literally cannot see the session it is meant to extract. If you reach for `Task(subagent_type=…)` here, stop: run the skill inline instead. - **Trigger.** The Stop hook nudges the still-live agent with text like "run the …
Read the whole file at its exact version.
How to install
mdr add lazyisefficient/agentic-os/memory-extraction@sha256:4e08b4293c0adc4fThe line at the top of this page pins the label git:20260716.7c29779, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_igj7hkr2oxg7qobf)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Jul 13, 2026 and Jul 16, 2026, more than one a day.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260716.7c29779 latest | 2026-07-16 | 7c29779 | 12,197 B | A | view · diff |
| git:20260714.8a80059 | 2026-07-14 | 8a80059 | 12,134 B | A | view · diff |
| git:20260713.e86d282 | 2026-07-13 | e86d282 | 12,042 B | A | view · diff |
| git:20260713.cf09f68 | 2026-07-13 | cf09f68 | 12,225 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (12197 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
lazyisefficient/agentic-os · 17 stars · license MIT · pushed 2026-10-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_igj7hkr2oxg7qobf GET https://markdownregistry.com/api/v1/resolve?ref=lazyisefficient/agentic-os/memory-extraction GET https://markdownregistry.com/api/v1/blob/4e08b4293c0adc4f51ae4708720a32f5b43e9d565124b508201b656d94a0f4aa
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.